Are you tired of the monotonous posed shots and find the perfectly balanced compositions too plain? Give this LoRA series a try. It is specifically designed to simulate cinematic effects. Its mission is to infuse dynamism and vitality into the images, and its vision is to make ordinary pictures come alive.
If you'd like to support me and do more : ☕ https://ko-fi.com/vjleoliu ☕commissions open
1. Frame In Frame
A frame within a frame is the use of visual elements in a scene to border a subject, further drawing the focus to them. The first frame is the literal shape and border of the entire image. The second frame is then created within the image, hence the term. To create this additional frame, photographers and cinematographers often use windows, doors, or other foreground elements. Subjects can also be framed with background elements that create the shape around the subject. It does not always have to be rectangular or square, just a shape that borders a subject.
2. Motion Blur
Also known as motion blur, it refers to the distinct trails left by fast - moving objects in a static scene or in a series of pictures, such as in movies or animations. which is suitable for creating highly dynamic or impactful visuals.
3. Dutch Angle
Bid farewell to the steady and stable，this LoRA allows you to create compositions from tilted perspectives, making the images more dynamic.
Recommended Configuration
This LoRA has undergone extensive testing, and the example images are all generated in one go and have not undergone enlargement processing.
Weight: 0.6 - 1.2 (default 0.9)
Size: 768/1024/1536 (default 1024)
Guidance Condition: 2.5 - 3.5 (default 3.5)
Steps: 20 - 40 (compatible with the turbo acceleration model, default 8 steps)
Sampler: euler (simple)
Support WebUI/ComfyUI. After testing, the effect of ComfyUI is better. It is recommended to use it together with my workflow.
OK! The above is all the content for this time. If you have any questions, welcome to leave a message/return pictures/like/follow. It would be great to have a combo of all these actions.
→→→→→→ Get more resources ←←←←←←
Description
Copyright Statement:
Some people have been abusing my model all the time. Hereby, I solemnly declare that my model is only for learning and communication purposes. Users should follow the community agreements and relevant national laws and regulations. Any individual or institution is prohibited from using it in any public or commercial fields without permission. Violators will be prosecuted.
FAQ
Comments (7)
works well with other LoRAs except for the face model LoRAs.
Which face LoRA do you use? I'd like to give it a try.
@vjleoliu ana de armas from el_fluppe
@JunkieMonkey69 is this one? https://civitai.com/models/667718/ana-de-armas-flux
@vjleoliu yes i used it 1.0 strength with yours in 0.8 to 1 strength
@JunkieMonkey69 OK. I'll do the test later and post the results.
@JunkieMonkey69 I tested four sets of prompt words, two sets from yours and two sets from mine, and then posted the generated results. Judging from the results, the combination of the two LoRAs didn't cause the expected chaos. On the contrary, it presented a great cinematic texture. Perhaps it's because both are sourced from movie materials. In my opinion, there is no problem at all. So, I'm not sure how to help you improve your generated results. If you have any further questions, feel free to leave a message.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.